数据集 flower_photos
数据预处理
INPUT_DATA = 'F://dl_dataset//flower_photos' OUTPUT_FILE = 'flower_processed_data.npy' training_images = [] training_labels = [] testing_images = [] testing_labels = [] validation_images = [] validation_labels = [] current_label = 0 for i in os.listdir(INPUT_DATA): path = os.path.join(INPUT_DATA, i).replace('//', '\\') if not os.path.isdir(path): continue for j in os.walk(path): for k in j[2]: filename = os.path.join(j[0], k) img = Image.open(filename) img = img.resize((299, 299)) image_value = np.array(img) # 随机划分数据 chance = np.random.randint(100) if chance < 10: validation_images.append(image_value) validation_labels.append(current_label) elif chance < 20: testing_images.append(image_value) testing_labels.append(current_label) else: training_images.append(image_value) training_labels.append(current_label) current_label += 1 # 将训练数据乱序 state = np.random.get_state() np.random.shuffle(training_images) np.random.set_state(state) np.random.shuffle(training_labels) out = np.asarray([training_images, training_labels, validation_images, validation_labels, testing_images, testing_labels]) np.save(OUTPUT_FILE, out)
存储为 npy 文件
迁移学习-finetune
import numpy as np import tensorflow as tf import tensorflow.contrib.slim as slim # 加载通过TensorFlow-Slim定义好的inception_v3模型。 import tensorflow.contrib.slim.python.slim.nets.inception_v3 as inception_v3 INPUT_DATA = 'flower_processed_data.npy' # 处理好之后的数据文件。 TRAIN_FILE = 'train_dir/model' # 保存训练好的模型的路径。 CKPT_FILE = 'inception_v3.ckpt' # 预训练模型参数 # 定义训练中使用的参数。 LEARNING_RATE = 0.0001 STEPS = 300 BATCH = 32 N_CLASSES = 5 CHECKPOINT_EXCLUDE_SCOPES = 'InceptionV3/Logits,InceptionV3/AuxLogits' # fine_tune 参数 TRAINABLE_SCOPES = 'InceptionV3/Logits,InceptionV3/AuxLogits' # 需要训练的网络层参数名称，在fine-tuning的过程中就是最后的全联接层。 def get_tuned_variables(): # 获取所有需要从谷歌训练好的模型中加载的参数。 exclusions = [scope.strip() for scope in CHECKPOINT_EXCLUDE_SCOPES.split(',')] variables_to_restore = [] # 枚举inception-v3模型中所有的参数，然后判断是否需要从加载列表中移除。 for var in slim.get_model_variables(): excluded = False for exclusion in exclusions: if var.op.name.startswith(exclusion): excluded = True break if not excluded: variables_to_restore.append(var) return variables_to_restore def get_trainable_variables(): # 获取所有需要训练的变量列表 scopes = [scope.strip() for scope in TRAINABLE_SCOPES.split(',')] variables_to_trian = [] # 枚举所有需要训练的参数前缀，并通过这些前缀找到所有需要训练的参数。 for scope in scopes: variables = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope) variables_to_trian.extend(variables) return variables_to_trian def main(): # 加载预处理好的数据。 processed_data = np.load(INPUT_DATA) training_images = processed_data[0] training_labels = processed_data[1] validation_images = processed_data[2] validation_labels = processed_data[3] testing_images = processed_data[4] testing_labels = processed_data[5] n_training_example = len(training_images) images = tf.placeholder(tf.float32, [None, 299, 299, 3], name='input_images') labels = tf.placeholder(tf.int64, [None], name='labels') # 定义inception-v3模型。因为谷歌给出的只有模型参数取值，所以这里 # 需要在这个代码中定义inception-v3的模型结构。虽然理论上需要区分训练和 # 测试中使用到的模型，也就是说在测试时应该使用is_training=False，但是 # 因为预先训练好的inception-v3模型中使用的batch normalization参数与 # 新的数据会有出入，所以这里直接使用同一个模型来做测试。 with slim.arg_scope(inception_v3.inception_v3_arg_scope()): logits, _ = inception_v3.inception_v3(images, num_classes=N_CLASSES, is_training=True) # 获取需要训练的变量 trainable_variables = get_trainable_variables() tf.losses.softmax_cross_entropy(tf.one_hot(labels, N_CLASSES), logits, weights=1.0) train_step = tf.train.RMSPropOptimizer(LEARNING_RATE).minimize(tf.losses.get_total_loss(), var_list=trainable_variables) ### 固定部分参数，优化其他参数 train_step = tf.train.RMSPropOptimizer(LEARNING_RATE).minimize(tf.losses.get_total_loss()) ### 优化全部参数 with tf.name_scope('evaluation'): correct_prediction = tf.equal(tf.arg_max(logits, 1), labels) # 计算正确率 evaluation_step = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) # 定义加载Google训练好的Inception-v3模型的Saver load_fn = slim.assign_from_checkpoint_fn( CKPT_FILE, get_tuned_variables(), ignore_missing_vars=True) saver = tf.train.Saver() with tf.Session() as sess: init = tf.global_variables_initializer() sess.run(init) load_fn(sess) # 加载 预训练 参数 start = 0 end = BATCH for i in range(STEPS): sess.run(train_step, feed_dict={images: training_images[start: end], labels: training_labels[start: end]}) if i % 30 == 0 or i + 1 == STEPS: saver.save(sess, TRAIN_FILE, global_step=i) validation_accuracy = sess.run(evaluation_step, feed_dict={images: validation_images, labels: validation_labels}) print('Step %d: Validation accuracy = %.1f%%' % (i, validation_accuracy * 100.0)) start = end if start == n_training_example: start = 0 end = start + BATCH if end > n_training_example: end = n_training_example # 在最后的测试数据上测试正确率 test_accuracy = sess.run(evaluation_step, feed_dict={images: testing_images, labels: testing_labels}) print('Final test accuracy = %.1f%%' % (test_accuracy * 100)) if __name__ == '__main__': main()
全部更新，训练慢，但是效果还行
Step 0: Validation accuracy = 25.6% Step 30: Validation accuracy = 26.4% Step 60: Validation accuracy = 48.0% Step 90: Validation accuracy = 79.3% Step 120: Validation accuracy = 88.6% Step 150: Validation accuracy = 92.3% Step 180: Validation accuracy = 93.2% Step 210: Validation accuracy = 96.0% Step 240: Validation accuracy = 94.9% Step 270: Validation accuracy = 94.6% Step 299: Validation accuracy = 94.6% Final test accuracy = 92.4%
部分更新，训练快，但是效果不行，当然你可以继续训练看看效果
Step 0: Validation accuracy = 25.0% Step 30: Validation accuracy = 25.3% Step 60: Validation accuracy = 30.1% Step 90: Validation accuracy = 32.7% Step 120: Validation accuracy = 42.0% Step 150: Validation accuracy = 52.8% Step 180: Validation accuracy = 53.7% Step 210: Validation accuracy = 59.7% Step 240: Validation accuracy = 61.9% Step 270: Validation accuracy = 66.5% Step 299: Validation accuracy = 67.0% Final test accuracy = 67.0%
参考资料：
https://www.jianshu.com/p/0237ebbee5d5
https://www.jianshu.com/p/a4fbe308b7b8
